7603 results about "Biologic marker" patented technology

A federated distributed computational system enables secure oncological therapy optimization through robotic integration. The system establishes a distributed graph architecture with secure communication channels connecting computational nodes, implementing encryption protocols for cross-institutional data exchange. Each node contains processing capabilities for fluorescence-guided imaging, uncertainty quantification, and expert knowledge integration while maintaining hierarchical knowledge graphs of oncological biomarkers, interventions, and outcomes. The system coordinates domain-specific knowledge through token-space communication and implements an advanced robotic integration system for surgical interventions using spatiotemporal tumor mapping, multi-modal fluorescence imaging, surgical robot coordination, and space-time stabilized mesh management. Key capabilities include wavelength-specific multi-modal fluorescence detection, combined epistemic and aleatoric uncertainty estimation, tensor-based data integration with adaptive dimensionality control, and light cone search for adaptive treatment optimization—all while maintaining strict privacy controls.

The invention provides a technical condition prediction method for a tunnel civil engineering structure, and relates to the technical field of traffic control monitoring systems.A biological acoustic composite sensing system comprising a distributed optical fiber acoustic sensing system and microorganism sample collection and analysis is constructed, and acoustic depth mode characteristics are mined by applying a deep learning model; the microbial dynamic biomarker is analyzed and identified by using bioinformatics; multi-modal information, a domain knowledge graph and a causal inference algorithm are fused, and a dynamic causal network model for revealing an internal driving relation in the degradation process is constructed; further, training and applying an adaptive neural network prediction model based on causal driving and fusing physical and biochemical mechanism constraints, and carrying out probabilistic prediction on future technical conditions of the tunnel; and executing anti-fact reasoning by using the causal network and the prediction model, and generating and optimizing an intervention strategy of cooperation of physical measures and biochemical measures. According to the method, the accuracy and advance of tunnel structure state prediction can be remarkably improved.

The present disclosure, in some aspects, provides one or more disease state-associated genes for repeat expansion diseases (e.g., a repeat expansion disease associated with spliceopathy, such as DM1). In some embodiments, each of the disease-state associated gene described herein is a disease-state associated gene for a repeat expansion disease (e.g., DM1). Methods of measuring the splicing activity of disease state- associated genes, e.g., for determining disease state and monitoring patient as well as treatment efficacy are also provided.

A deep learning-based virtual HER2 IHC staining method uses a conditional generative adversarial network that is trained to rapidly transform autofluorescence microscopic images of unlabeled / label-free breast tissue sections into bright-field equivalent microscopic images, matching the standard HER2 IHC staining that is chemically performed on the same tissue sections. The efficacy of this staining framework was demonstrated by quantitative analysis of blindly graded HER2 scores of virtually stained and immunohistochemically stained HER2 whole slide images (WSIs). A second quantitative blinded study revealed that the virtually stained HER2 images exhibit a comparable staining quality in the level of nuclear detail, membrane clearness, and absence of staining artifacts with respect to their immunohistochemically stained counterparts. This virtual staining framework bypasses the costly, laborious, and time-consuming IHC staining procedures in laboratory, and can be extended to other types of biomarkers to accelerate the IHC tissue staining and biomedical workflow.

The invention relates to the technical field of test optimization, in particular to a biomedical test optimization system based on a graphic model, which comprises a data collection module, a graphic weight adjustment module, a path exploration module and an optimization adjustment module. According to the method, the drug concentration and the reaction data of the biomarker are synchronously integrated through real-time data, the whole test process can be covered, real-time updating and accurate mapping of the data can be ensured, the reliability and effectiveness of the test are greatly enhanced, and the dynamic data can be obtained through updating the weights of nodes and edges in a graphic model in real time. The model can accurately reflect the actual interaction effect between drugs, path analysis and pharmacological action relation marking are carried out by utilizing updated data, the pertinence and scientificity of the test are further enhanced, key variables and action paths can be quickly identified, a drug combination scheme is optimized, the research and development efficiency and cost control are remarkably improved, and the research and development efficiency is improved. The research and development period of the medicine is greatly shortened.

The invention discloses a breast cancer immunohistochemical index and typing prediction method and system. The prediction method comprises the following steps: acquiring a breast ultrasound image and a breast magnetic resonance image of a patient; performing preprocessing and quality control on the mammary gland ultrasonic image and the mammary gland magnetic resonance image; performing breast lesion area segmentation by adopting a deep learning model to obtain segmented lesion areas; based on the segmented lesion area, extracting multi-modal radiomics characteristics of the breast ultrasonic image and the breast magnetic resonance image; fusing the multi-modal radiomics characteristics of the breast ultrasound image and the breast magnetic resonance image, constructing a machine learning model, and performing immunohistochemical index prediction to obtain an immunohistochemical index prediction result; and performing breast cancer molecular typing analysis according to the immunohistochemical index prediction result. By fusing the multi-modal image information, the tumor features can be described more comprehensively, and the accuracy of biomarker prediction is improved.

The invention discloses a combination of different nucleic acid aptamers with known 291 targets, sequences of the nucleic acid aptamers of the combination are subjected to sequencing analysis through a single-cell high-throughput sequencing technology, and a cell map aiming at peripheral blood-derived mononuclear cells of a biliary tract cancer patient can be constructed. The nucleic acid aptamers covered by the combination have high specific affinity to molecular targets of the nucleic acid aptamers, and after the two ends of the nucleic acid aptamer sequences extend to adapt to joints of a commercial sequencing platform, high-throughput sequencing is carried out on the nucleic acid aptamer sequences which are combined with the surfaces of mononuclear cells and are provided with the sequencing joints; high-throughput analysis of the biomarkers on the surface of the peripheral blood-derived mononuclear cell of a biliary tract cancer patient can be realized, so that the cell map of the peripheral blood-derived mononuclear cell of the biliary tract cancer is constructed.

The invention relates to the technical field of biomarkers, in particular to a blood biomarker combination for prediction and auxiliary diagnosis of ovarian reserve hypofunction (DOR), a corresponding detection kit and application of the blood biomarker combination. According to the invention, the content change of the nicotinamide mononucleotide (NMN) and the metabolite combination thereof in serum or plasma is screened for the first time and can be used as a detection index for predicting the ovarian reserve function decline. Based on the biomarker combination, the invention further provides an in-vitro detection kit containing a related standard substance, an internal standard solution and an extracting solution, and a data analysis method combined with a random forest model, so that an individual with a normal ovarian reserve function and an individual with hypofunction can be accurately distinguished. The method is noninvasive, simple, convenient, high in sensitivity and suitable for early recognition and layered screening of clinical ovarian reserve hypofunction.

Methods for predicting health characteristic may include: obtaining patient medical information that includes protein data; a machine-learning model based on concordance with the characteristic, the patient medical information, a time-frame for prediction, or in the protein data. Different models may have been trained using different groupings of training patient data, trained to predict different characteristics, trained or evaluated using different biomarkers, trained using proteins, protein groups, or protein categories listed in Tables M through R, or evaluated for different time-frames. The selected model may be used to generate the prediction using the patient medical information. A model may be generated by pre-processing medical information, generating an ensemble of models; determining a sensitivity of variables of the medical information to identify a subset of variables; and training a machine-learning model using the subset.

Platinum-acridines and analogs thereof as cytotoxic agents for cancer treatment. Also provided methods of using hMATE1 (SLC47A1) as a biomarker to identify tumors that are likely to respond to the agents, and epigenetically sensitizing tumor tissue to anticancer drugs targeting this membrane transporter.

The invention discloses an enteritis patient condition severity risk early warning method, a medium and equipment. The method comprises the following steps: acquiring a borborygmus original signal and a clinical multi-dimensional physiological parameter sequence through a sensing device; constructing a borborygmus dynamic characteristic spectrum based on the borborygmus original signal to generate an acoustic biomarker time sequence; inputting the acoustic biomarker time sequence and the clinical multi-dimensional physiological parameter sequence into a multi-modal fusion early warning model to obtain an intestinal inflammation risk index; executing a signal quality self-evaluation process and generating a data quality warning code when the signal quality is abnormal; triggering a multi-node collaborative monitoring mechanism based on the risk index to generate an intestinal state multi-dimensional situation map; establishing an individualized risk baseline and generating a graded early warning instruction; and finally outputting a comprehensive early warning report. According to the method, multi-modal fusion analysis of the borborygmus signal and the clinical parameters is realized, the accuracy and timeliness of illness state early warning are remarkably improved through dynamic risk assessment and signal quality monitoring, and a reliable basis is provided for clinical decision making.

An information processing apparatus (100) according to one embodiment of the present disclosure includes a guide image generation unit (133) configured to sum up a plurality of images each including spectral information regarding a biomarker, and perform a division on a result by a number of summed images to generate a guide image for correction.

The invention relates to the technical field of cardiovascular medicine, in particular to an automatic alarm system for cardiovascular medicine, which comprises a biomarker analysis module, a physiological parameter analysis module, a cardiovascular risk assessment module, a cardiovascular early warning adjustment module and an alarm trigger notification module. According to the invention, by integrating real-time monitoring of blood biomarkers and cardiovascular physiological parameters, the early recognition capability of cardiovascular disease risks is improved, key biomarkers are dynamically measured and compared with historical marker data, and subtle physiological changes can be captured at the early stage of asymptomatic conditions, so that potential cardiovascular events are warned; through correlation analysis of electrocardiogram, blood pressure and pulse waveforms, the system can accurately draw a comprehensive image of cardiovascular functions, so that more targeted monitoring and intervention are implemented, timeliness and accuracy of medical response are ensured, doctors can formulate targeted monitoring schemes according to real-time data, and the monitoring efficiency is improved. Therefore, deterioration or occurrence of cardiovascular events of patients can be effectively prevented.

Provided herein are methods and systems for diagnosing pathological conditions using machine learning and artificial intelligence models. An exemplary method can include loading an abundance matrix that represents mass spectrometry reads of a sample of a plurality of volatile organic compounds (VOCs) extracted from a biological sample. The abundance matrix can represent each of the plurality of VOCs in a mass-to-charge ratio dimension, an abundance dimension, and a retention time dimension. The method can include providing the abundance matrix to a machine-learning model. The machine- learning model can be trained on abundance matrixes of biomarkers of VOCs collected from healthy and diseased subjects. The method can include receiving, from the machine-learning model, a prediction of a state of a disease state.

The invention provides a brand new programmed death ligand 1 (PD-L1) level and immunotherapy response prediction algorithm based on the application of a deep learning technology in medical images in combination with methods of multi-modal feature fusion, a self-attention mechanism, adversarial learning and the like. The algorithm comprises the following steps of data preprocessing, encoder feature extraction, radiomics feature extraction, multi-modal feature fusion, PD-L1 level prediction and immunotherapy response prediction. According to the invention, the pathological image (Hamp; according to the method, a CT image (e.g., E staining section), a CT image and clinical data are integrated into a deep learning model for predicting the PD-L1 level of an esophageal squamous cell carcinoma (ESCC) patient. In addition, by extracting PD-L1 features of an immunotherapy patient, a model for predicting immunotherapy response is constructed. By fusing multi-modal data, auc of the model in a PD-L1 prediction task is equal to 0.835, auc of the model in an immunotherapy reaction task is equal to 0.806, a new thought and method are provided for related research in the field of tumor treatment, and beneficial reference is provided for clinical treatment.

The invention provides a human body biological age detection method based on DNA methylation, which comprises the following steps: step S1, aiming at at least one subject, collecting a peripheral blood sample of the subject, and extracting DNA in blood from the sample; the method comprises the following steps: S1, extracting DNA, S2, measuring a methylation map of the extracted DNA to obtain detailed information of the methylation state of the DNA, and S3, calculating a corresponding methylation rate according to the strength of a methylation signal and a non-methylation signal in the obtained methylation map; and step S4, inputting the calculated DNA methylation rate into a biological age model obtained by pre-training to obtain the biological age corresponding to the subject. The method has the beneficial effects that the biological age can be accurately predicted by acquiring methylation information of DNA data, a novel biomarker-based assessment means is provided, and the method has important application value in health management, disease risk assessment and the like.

The invention discloses a blood extracellular vesicle miRNA (micro Ribonucleic Acid), miRNAs (micro Ribonucleic Acid) hsa-miR-150-3p, hsa-miR-150-5p, hsa-miR-335-3p, hsa-miR-375, hsa-miR-4433b-5p and hsa-miR-4732-5p, which can be used as biomarkers for early diagnosis of lung cancer, so that the blood extracellular vesicle miRNA can be used for preparing a chip, a detection reagent or a detection kit for early diagnosis of lung cancer. The blood extracellular vesicle miRNA biomarker disclosed by the invention has high sensitivity and high specificity on early diagnosis of lung cancer, so that false positive caused by a traditional diagnosis method can be reduced, and the miRNA biomarker has a potential good clinical application value.

According to the building system for enhancing the large language model based on the knowledge graph, the LLM and the knowledge graph (KG) are combined, the initial response of the model is improved by utilizing verifiable information in the knowledge graph, and therefore factual errors in the reasoning process are remarkably reduced. The KAR framework shows high adaptability, and shows excellent performance in various open-source LLMs (Logistics Language Models). In particular, KAR can promote the discovery of new uses of existing drugs by identifying potential drug-cancer associations, and can assist in predicting drug resistance by analyzing related biomarkers and genetic mechanisms. In order to evaluate knowledge network question and answer tasks in the field of biomedicine, a benchmark test named cross-domain tumor question and answer is developed. The KAR framework significantly improves the accuracy and practicability of the LLM in the field of biomedicine, and shows the excellent performance of the LLM in biomedicine questions and answers.

The invention belongs to the field of electrochemical biosensors, discloses a preparation method of an electrochemical biosensor capable of being used for multi-mode sweat detection, and particularly provides a single-electrode multifunctional arrangement method in a three-electrode system. A sensor material with high sensitivity and high selectivity is prepared, then the sensor material is printed through screen printing and assembled into a portable device to achieve simultaneous detection of multiple biomarkers in sweat, and the preparation method comprises the steps of selection and modification of an electrode material, sensor assembly and integration of a signal acquisition and analysis system. Through innovative material design and process optimization, the sensor not only can acquire information of various biomarkers in sweat in real time, but also can provide reliable data analysis, and shows excellent long-term stability and anti-interference capability in practical application. The technology provides an effective and reliable solution for real-time health monitoring.

A personalized diagnostic system for healthcare, comprehensive: a deep learning framework trained on a diverse dataset of medical images to analyze and interpret medical images; a data fusion module that integrates imaging data with non-imaging patient data such as electronic health records (EHRs), genetic information, and biomarker profiles; a high-performance computing system that uses GPUs (Graphics Processing Units) and TPUs (Tensor Processing Units) for real-time and batch processing of medical data; an intuitive user interface that displays diagnostic results, visualizations of medical images, and interactive functions for adjusting diagnostic parameters; a continuous learning mechanism that updates the deep learning models based on new data and expert feedback; a cloud-based platform for managing the continuous learning process, including the storage of anonymized patient data and diagnostic results; an explanatory module that provides detailed explanations of the diagnostic process using techniques such as Grad-CAM (Gradient-weighted Class Activation Mapping) and SHAP (SHapley Additive exPlanations); and a role-based access control (RBAC) mechanism to secure patient data.

The disclosure provides technologies that permit detection and / or characterization of brain biomarkers (e.g., disease-associated biomarkers) in non-CNS samples, including by liquid biopsy (e.g., blood, serum, etc.). Among other things, the present disclosure demonstrates that ultrasound opening of the blood brain barrier can achieve detectable increases in brain-derived materials (e.g., brain-derived proteins, neuron-derived extracellular vesicles, and / or cell-free DNA) in readily-sampled systemic liquids.

The invention relates to the technical field of biological detection, and particularly discloses a marker combination for detecting Alzheimer's disease, which comprises the following markers: beta amyloid protein 1-40, beta amyloid protein 1-42, phosphorylated Tau217 protein, phosphorylated Tau181 protein, phosphorylated Tau231 protein, neurofilament light chain protein and colloidal fiber acidic protein. The invention also discloses application of the marker combination for detecting the Alzheimer's disease in single molecule detection. The application comprises the following steps: S1, preparing standard solutions with different concentrations of the markers; s2, detecting the standard solutions with different concentrations of each marker by adopting a single molecule array analysis technology, and counting corresponding single molecule signal numbers; and S3, drawing a standard curve of each marker according to the single molecule signal numbers corresponding to the standard solutions with different concentrations of each marker. The method has the advantages that the overall performance of the AD disease biomarker combination can be accurately evaluated, and the reliability and accuracy of AD disease markers in clinical application are improved.

The invention relates to an ovarian reserve hypofunction prediction method based on multi-data fusion, and the technical scheme comprises the following steps: regularly collecting biomarker data related to ovarian reserve, including anti-mullerian canal hormone AMH, follicle stimulating hormone FSH, luteinizing hormone LH, estradiol E2, and ultrasonic image data including follicle quantity and ovarian volume; acquiring dynamic change curve data and capturing the change trend of the ovarian reserve function when the acquisition time point covers the key stage of the menstrual cycle; analyzing the biomarker data acquired for multiple times by using an LSTM deep learning model, and modeling a change trend of the ovarian reserve function of each patient along with time; by analyzing the periodic fluctuation of AMH and FSH biomarkers, the decline time node of the ovarian reserve function in the future is predicted; and on the basis of the LSTM deep learning model of S1.1, performing personalized risk assessment in combination with individual characteristics of patients including age, genes, lifestyles and disease histories.

The invention provides a traditional Chinese medicine meridian prescription system based on multi-omics integration analysis of extracellular vesicles, and the system comprises a data collection module which is used for collecting biopsy sample information of different groups of individuals based on related experiments and literatures of traditional Chinese medicine meridian prescription treatment; the data processing module is used for obtaining and preprocessing extracellular vesicle data and intestinal flora data based on biopsy sample information; the multi-omics integration module is used for obtaining multi-omics integration data; the discovery and verification module is used for obtaining the potential menstrual prescription drug effect evaluation biomarker and performing experimental verification on the potential menstrual prescription drug effect evaluation biomarker to obtain a verification result; and the system biology application module is used for obtaining a regulatory mechanism of the extracellular vesicles in a biological system based on construction of a gene-protein-metabolite interaction network. The invention can comprehensively reveal the pharmacodynamic mechanism of the traditional Chinese medicine menstrual prescription, and provides strong technical support and application prospect for the modern, scientific and internationalized development of traditional Chinese medicines.

Disclosed herein are methods that aid in the diagnosis and evaluation of a human subject that has sustained or may have sustained an injury to the head, such as mild or moderate to severe traumatic brain injury (TBI), using an early biomarker, ubiquitin carboxy-terminal hydrolase L1 (UCH-L1). Also disclosed here are methods that aid in determining whether a human subject that has sustained an injury or may have sustained to the head would benefit from and thus receive a head computerized tomography (CT) scan based on the levels of UCH-L1. These methods involve detecting levels and changes in levels of UCH-L1 in one or more samples taken from a human subject at time points within 24 hours after the subject has sustained or may have sustained an injury to the head.

The invention relates to the technical field of biological medicine, and discloses a pharmaceutical composition of paclitaxel dimer prodrug nanoparticles and a traditional Chinese medicine compound and application of the pharmaceutical composition, and the pharmaceutical composition is composed of Qiyuansanlong prescription freeze-dried powder and paclitaxel dimer prodrug nanoparticles; wherein the paclitaxel dimer prodrug nanoparticles comprise one of NQO1 response type PTX dimer prodrug nanoparticles (PTX-Q-PTX NPs) or GSH (glutathione) response type PTX dimer prodrug nanoparticles (PTX-SeSe-PTXNPs), and the paclitaxel dimer prodrug nanoparticles comprise one of NQO1 response type PTX dimer prodrug nanoparticles (PTX-Q-PTX NPs) and GSH response type PTX dimer prodrug nanoparticles (PTX-SeSe-PTXNPs). According to the pharmaceutical composition disclosed by the invention, a traditional Chinese and western medicine synergistic treatment system is innovatively constructed, and the advantage of multi-dimensional synergistic interaction is shown. Firstly, an NQO1 / GSH double-response type intelligent release system is adopted, and a biomarker highly expressed by tumor tissue can be specifically responded to realize precise drug release, so that the PTX concentration in tumors is improved compared with that of a traditional dosage form, and meanwhile, the drug circulation time is prolonged. Secondly, the active ingredients in the Qiyuansanlong prescription freeze-dried powder can significantly down-regulate the PD-L1 expression level, synergistically enhance CD4 + T and CD8 + T cell infiltration, and form chemical-immune dual killing effects.

The invention discloses an autophagy biomarker related to depression, a risk assessment model and application of the autophagy biomarker. A group of autophagy related biomarkers for auxiliary diagnosis of depression are screened out through multi-dimensional screening of large sample data and a machine learning algorithm, the autophagy related biomarkers comprise the following genes: GABARAPL2, RB1CC1, FOS and ULK1, and differential expression of the autophagy related biomarkers is proved in chronic stress induced depression-like mouse cortical brain tissues. The invention also provides a risk assessment model for auxiliary diagnosis of depression, a logistic regression model is constructed by taking the biomarker as a feature, a score formula and a risk boundary value of depression risk assessment are determined, and multi-aspect assessment is carried out on the prediction performance of the model. The prediction model has good prediction accuracy and calibration degree, can efficiently and conveniently realize early diagnosis of depression, and improves the accuracy of depression treatment.

The invention discloses a pain management method based on bioelectrical impedance data and a machine learning algorithm, and relates to the technical field of medical health, and the method comprises the steps: carrying out the phase delay analysis of an impedance phase spectrum matrix, calculating the change rate of a phase angle of each frequency point along with time, and obtaining the maximum phase lag time; according to the temperature field sequence and the maximum phase lag time, time-space registration is carried out through a multi-modal data fusion method and impedance modulus changes of the corresponding areas, and a pain biomarker feature library is generated; through a bidirectional LSTM and a cross attention fusion method, time sequence modeling and cross-modal correlation analysis are carried out on bioelectricity signal characteristics extracted by a sliding window and historical pain data, a dynamic evolution rule of pain development is captured, a pain management triple containing pain intensity, intervention response and prognosis evaluation is generated, and a pain management result is obtained. And a quantitative basis is provided for personalized treatment.

The invention belongs to the technical field of medical pathological images, and particularly relates to a multi-instance multi-task learning pan cancer biomarker prediction method and system, and the method comprises the steps: obtaining a full-view digital pathological image and pan cancer biomarker expression data of a solid tumor patient; performing preprocessing and feature extraction based on the full-view digital pathological image to obtain a pathological feature data set; based on the pathological feature data set, inputting the pathological feature data set into a twin multi-example full convolutional network model for training to obtain pathological low-dimensional features, and calculating an attention score corresponding to each pathological feature in combination with a linear attention mechanism; and in combination with each pathologic low-dimensional feature and the corresponding attention score, calculating to obtain a pathologic depth feature, and inputting the pathologic depth feature into a multi-task classification prediction model for classification prediction to obtain a prediction result of each biomarker in the pan cancer.

The invention relates to the field of medical detection, in particular to a group of biomarkers for diagnosing hypertension in children, a kit and application of the biomarkers. According to the method, tongue coating / intestinal tract samples of obese children hypertensive patients, obese children and healthy people are collected, metagenome sequencing is carried out, sequencing data statistics is carried out by using bioinformatics, tongue coating / intestinal tract florae related to diseases are found, the tongue coating / intestinal tract florae and disease information are integrated, a flora biomarker combination is obtained, and the method is applied to diagnosis and treatment of the hypertensive patients, the obese children and the healthy people. The hypertensive patients of obese children can be detected to the maximum extent through the binary classification prediction model constructed through the combination.